Files
kernel_google_wahoo/include/linux
Douglas Miller b3c8c31ed2 percpu-refcount: fix reference leak during percpu-atomic transition
commit 966d2b04e070bc040319aaebfec09e0144dc3341 upstream.

percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().

This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:

__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0

Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.

The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.

Fixes: e625305b39 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: e625305b39 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-02-09 08:02:46 +01:00
..
2016-03-03 15:07:26 -08:00
2015-10-01 12:48:11 -07:00
2015-06-25 11:49:31 +03:00
2015-10-17 21:22:08 -07:00
2015-10-07 18:08:15 +01:00
2015-08-27 20:47:09 +01:00
2016-08-20 18:09:25 +02:00
2016-03-09 15:34:52 -08:00
2015-11-07 10:40:47 -07:00
2015-09-08 15:35:28 -07:00
2016-07-27 09:47:33 -07:00
2015-10-18 10:14:39 -07:00
2015-10-30 01:47:27 -04:00
2015-06-24 17:49:45 -07:00
2015-09-08 15:35:28 -07:00
2016-04-20 15:42:02 +09:00
2015-10-23 05:44:28 -07:00
2015-08-27 19:40:58 -04:00
2015-10-01 15:06:43 +02:00
2015-10-13 19:01:25 +02:00
2015-06-25 12:06:45 +02:00
2016-10-28 03:01:30 -04:00
2015-08-18 15:49:15 -07:00
2015-07-28 08:50:42 +01:00
2015-11-23 09:44:58 +01:00
2015-10-27 18:55:31 -07:00
2015-06-24 17:49:41 -07:00
2015-10-20 22:10:45 +08:00
2015-07-21 10:39:05 -07:00
2015-06-25 04:20:04 -04:00
2016-03-03 15:07:28 -08:00
2015-09-10 13:29:01 -07:00
2015-09-10 13:29:01 -07:00
2015-11-06 17:50:42 -08:00
2016-12-08 07:15:24 +01:00
2015-10-09 17:00:32 -04:00
2015-10-06 17:08:19 +02:00
2015-10-22 08:59:18 -07:00
2015-05-26 15:23:23 +02:00
2015-06-25 01:13:43 +02:00
2016-09-30 10:18:37 +02:00
2016-10-28 03:01:30 -04:00
2015-06-25 17:00:39 -07:00
2016-04-12 09:08:35 -07:00
2015-08-17 11:25:28 -07:00
2015-10-01 09:57:59 -07:00
2015-10-19 01:01:21 +02:00
2016-06-01 12:15:52 -07:00
2015-11-23 09:44:58 +01:00
2015-12-04 08:38:42 -07:00
2015-12-13 14:30:59 -08:00
2015-11-13 20:34:33 -05:00
2015-09-08 15:35:28 -07:00